ntail 0.0.7 → 0.0.8

data/VERSION

@@ -1 +1 @@
-0.0.7
+0.0.8

data/lib/ntail/log_line.rb

@@ -102,131 +102,5 @@ module NginxTail
       ]
     end
   
-    CONVERSIONS = [
-  
-      :to_date,
-      :to_date_s,
-      
-      :to_agent,
-      :to_agent_s,
-
-      :to_host_name,
-      :to_refering_website,
-      
-      :to_country_s,
-      :to_city_s,
-    
-    ]
-
-    def self.log_subcomponent?(subcomponent)
-      # TODO replace with some clever meta-programming...
-      SUBCOMPONENTS.include?(subcomponent)
-    end
-    
-    def self.log_component?(component)
-      # TODO replace with some clever meta-programming...
-      COMPONENTS.include?(component)
-    end
-    
-    def self.log_conversion?(conversion)
-      # TODO replace with some clever meta-programming...
-      CONVERSIONS.include?(conversion)
-    end
-    
-    def self.log_directive?(directive)
-      (directive == :full) or log_conversion?(directive) or log_component?(directive) or log_subcomponent?(directive)
-    end
-
-    #
-    # extraction filters for log line components
-    #
-
-    def self.regexp_for_remote_address(remote_address)
-      Regexp.compile(/^(#{remote_address}) /)
-    end
-
-    def self.regexp_for_request(request)
-      Regexp.compile(/^([^"]+) "([^"]*#{request}[^"]*)" /)
-    end
-
-    def self.regexp_for_status(status)
-      Regexp.compile(/ "([^"]+)" (#{status}) /)
-    end
-
-    def self.regexp_for_http_referer(http_referer)
-      Regexp.compile(/" .* "([^"]*#{http_referer}[^"]*)" "/)
-    end
-
-    def self.regexp_for_http_user_agent(http_user_agent)
-      Regexp.compile(/ "([^"]*#{http_user_agent}[^"]*)"$/)
-    end
- 
-    #
-    # validation of log line components
-    #
-
-    def self.valid_status?(status)
-      if /\A(\d{1,3})\Z/ =~ status
-        return $~.captures.all? { |i| 100 <= i.to_i and i.to_i < 600 }
-      end
-      return false
-    end
-
-    def self.valid_v4?(addr)
-      if /\A(\d{1,3})\.(\d{1,3})\.(\d{1,3})\.(\d{1,3})\Z/ =~ addr
-        return $~.captures.all? {|i| i.to_i < 256}
-      end
-      return false
-    end
-
-    def self.valid_request?(request) true ; end
-    def self.valid_referer?(referer) true ; end
-    def self.valid_user_agent?(user_agent) true ; end
-
-    #
-    # "GET /xd_receiver.html HTTP/1.1"
-    # "GET /crossdomain.xml HTTP/1.1"
-    # "GET /favicon.ico HTTP/1.1"
-    # "GET /robots.txt HTTP/1.0"
-    #
-
-    AUTOMATED_REQUESTS = [
-      Regexp.compile('^[A-Z]+ \/xd_receiver.html'),
-      Regexp.compile('^[A-Z]+ \/crossdomain.xml'),
-      Regexp.compile('^[A-Z]+ \/favicon.ico'),
-      Regexp.compile('^[A-Z]+ \/robots.txt'),
-      nil
-    ].compact!
-  
-    def self.automated_request?(request) !AUTOMATED_REQUESTS.detect { |automated_request_regexp| request.match(automated_request_regexp) }.nil? end
-    def      automated_request?()        self.class.automated_request?(self.request) ; end
-
-    # 
-    # subdirectories of the "public" folder in the web root,
-    # which - in a typical Rails setup - are served by nginx
-    #
-
-    STATIC_REPOS = %w{
-      flash
-      html
-      images
-      javascripts
-      movies
-      newsletters
-      pictures
-      stylesheets
-      xml
-    }
-
-    STATIC_URIS = STATIC_REPOS.map { |repo| Regexp.compile("^\/#{repo}\/") }
-  
-    def self.static_uri?(uri) !STATIC_URIS.detect { |static_uri_regexp| uri.match(static_uri_regexp) }.nil? end
-    def      static_uri?()    self.class.static_uri?(self.uri); end
-
-    STATIC_REQUESTS = STATIC_REPOS.map { |repo| Regexp.compile("^[A-Z]+ \/#{repo}\/") }
-  
-    def self.static_request?(request) !STATIC_REQUESTS.detect { |static_request_regexp| request.match(static_request_regexp) }.nil? end
-    def      static_request?()        self.class.static_request?(self.request) ; end
-
   end # class LogLine
 end # module NginxTail

data/lib/ntail/uri.rb

@@ -4,6 +4,79 @@ module NginxTail
     def self.included(base) # :nodoc:
       base.class_eval do
 
+        #
+        # files in the "public" folder of the web root
+        # which are requested automagically, by things
+        # like browsers, Facebook, search engines, ...
+        #
+
+        @@default_automatic_files = %w{
+          xd_receiver.html
+          crossdomain.xml
+          favicon.ico
+          sitemap.xml
+          robots.txt
+        }
+
+        @@automatic_files = [] ; @@automatic_uris = []
+
+        # mainly (solely?) for testing purposes...
+        def self.automatic_files()
+          @@automatic_files.dup
+        end
+
+        # mainly (solely?) for testing purposes...
+        def self.automatic_uris()
+          @@automatic_uris.dup
+        end
+
+        # mainly (solely?) for testing purposes...
+        def self.reset_automatic_files()
+          while !@@automatic_files.empty? ; @@automatic_files.pop ; end
+          while !@@automatic_uris.empty? ; @@automatic_uris.pop ; end
+          self.add_automatic_file(@@default_automatic_files)
+        end
+
+        def self.add_automatic_file(automatic_file)
+          if automatic_file.is_a? Array
+            # some ducktyping, so that we can also accepts arrays of values
+            automatic_file.each { |file| self.add_automatic_file(file) }
+          else
+            (@@automatic_files << automatic_file).uniq!
+            (@@automatic_uris << Regexp.compile("^\/#{automatic_file}")).uniq!
+          end
+        end
+
+        # populate with default values...
+        self.reset_automatic_files
+
+        def self.automatic_uri?(uri)
+          !@@automatic_uris.detect { |automatic_uri_regexp| uri.match(automatic_uri_regexp) }.nil?
+        end
+
+        #
+        # subdirectories of the "public" folder in the web root,
+        # which - in a typical Rails setup - are served by nginx
+        #
+
+        @@static_repos = %w{
+          flash
+          html
+          images
+          javascripts
+          movies
+          newsletters
+          pictures
+          stylesheets
+          xml
+        }
+
+        @@static_uris = @@static_repos.map { |repo| Regexp.compile("^\/#{repo}\/") }
+
+        def self.static_uri?(uri)
+          !@@static_uris.detect { |static_uri_regexp| uri.match(static_uri_regexp) }.nil?
+        end
+
         def self.to_uri_s(uri)
           uri || "-" # will be nil if $request == "-" (ie. "dodgy" HTTP requests)
         end
@@ -17,6 +90,14 @@ module NginxTail
     def to_uri_s
       self.class.to_uri_s(self.uri)
     end
+
+    def automatic_uri?
+      self.class.automatic_uri?(self.uri)
+    end
+
+    def static_uri?
+      self.class.static_uri?(self.uri)
+    end
     
   end
 end

data/ntail.gemspec

@@ -5,11 +5,11 @@
 
 Gem::Specification.new do |s|
   s.name = %q{ntail}
-  s.version = "0.0.7"
+  s.version = "0.0.8"
 
   s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
   s.authors = ["Peter Vandenberk"]
-  s.date = %q{2011-01-06}
+  s.date = %q{2011-01-10}
   s.default_executable = %q{ntail}
   s.description = %q{A tail(1)-like utility for nginx log files. It supports parsing, filtering and formatting individual log lines.}
   s.email = %q{pvandenberk@mac.com}
@@ -57,12 +57,13 @@ Gem::Specification.new do |s|
     "test/ntail/test_request.rb",
     "test/ntail/test_status.rb",
     "test/ntail/test_time_local.rb",
+    "test/ntail/test_uri.rb",
     "test/test_ntail.rb"
   ]
   s.homepage = %q{http://github.com/pvdb/ntail}
   s.licenses = ["MIT"]
   s.require_paths = ["lib"]
-  s.rubygems_version = %q{1.3.7}
+  s.rubygems_version = %q{1.4.1}
   s.summary = %q{A tail(1)-like utility for nginx log files}
   s.test_files = [
     "test/helper.rb",
@@ -77,11 +78,11 @@ Gem::Specification.new do |s|
     "test/ntail/test_request.rb",
     "test/ntail/test_status.rb",
     "test/ntail/test_time_local.rb",
+    "test/ntail/test_uri.rb",
     "test/test_ntail.rb"
   ]
 
   if s.respond_to? :specification_version then
-    current_version = Gem::Specification::CURRENT_SPECIFICATION_VERSION
     s.specification_version = 3
 
     if Gem::Version.new(Gem::VERSION) >= Gem::Version.new('1.2.0') then

data/test/ntail/test_uri.rb

@@ -0,0 +1,32 @@
+require 'helper'
+
+class TestUri < Test::Unit::TestCase
+
+  context "ntail" do
+
+    teardown do
+      # undo any changes the test may have made
+      NginxTail::LogLine.reset_automatic_files
+    end
+    
+    should "correctly identify a default automatic request" do
+      # directly via the helper function
+      # parsed from a raw log line
+      log_line = random_log_line(:uri => '/index.html')
+      assert !log_line.automatic_uri?      
+      log_line = random_log_line(:uri => '/robots.txt')
+      assert log_line.automatic_uri?      
+    end
+
+    should "correctly identify a custom automatic request" do
+      # directly via the helper function
+      # parsed from a raw log line
+      log_line = random_log_line(:uri => '/blegga.html')
+      assert !log_line.automatic_uri?
+      NginxTail::LogLine.add_automatic_file('blegga.html')
+      assert log_line.automatic_uri? 
+    end
+        
+  end
+
+end

metadata

@@ -1,13 +1,13 @@
 --- !ruby/object:Gem::Specification 
 name: ntail
 version: !ruby/object:Gem::Version 
-  hash: 17
-  prerelease: false
+  hash: 15
+  prerelease: 
   segments: 
   - 0
   - 0
-  - 7
-  version: 0.0.7
+  - 8
+  version: 0.0.8
 platform: ruby
 authors: 
 - Peter Vandenberk
@@ -15,13 +15,11 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2011-01-06 00:00:00 +00:00
+date: 2011-01-10 00:00:00 +00:00
 default_executable: ntail
 dependencies: 
 - !ruby/object:Gem::Dependency 
   type: :runtime
-  prerelease: false
-  name: rainbow
   version_requirements: &id001 !ruby/object:Gem::Requirement 
     none: false
     requirements: 
@@ -32,10 +30,10 @@ dependencies:
         - 0
         version: "0"
   requirement: *id001
+  prerelease: false
+  name: rainbow
 - !ruby/object:Gem::Dependency 
   type: :runtime
-  prerelease: false
-  name: user-agent
   version_requirements: &id002 !ruby/object:Gem::Requirement 
     none: false
     requirements: 
@@ -46,10 +44,10 @@ dependencies:
         - 0
         version: "0"
   requirement: *id002
+  prerelease: false
+  name: user-agent
 - !ruby/object:Gem::Dependency 
   type: :development
-  prerelease: false
-  name: shoulda
   version_requirements: &id003 !ruby/object:Gem::Requirement 
     none: false
     requirements: 
@@ -60,10 +58,10 @@ dependencies:
         - 0
         version: "0"
   requirement: *id003
+  prerelease: false
+  name: shoulda
 - !ruby/object:Gem::Dependency 
   type: :development
-  prerelease: false
-  name: bundler
   version_requirements: &id004 !ruby/object:Gem::Requirement 
     none: false
     requirements: 
@@ -76,10 +74,10 @@ dependencies:
         - 0
         version: 1.0.0
   requirement: *id004
+  prerelease: false
+  name: bundler
 - !ruby/object:Gem::Dependency 
   type: :development
-  prerelease: false
-  name: jeweler
   version_requirements: &id005 !ruby/object:Gem::Requirement 
     none: false
     requirements: 
@@ -92,10 +90,10 @@ dependencies:
         - 1
         version: 1.5.1
   requirement: *id005
+  prerelease: false
+  name: jeweler
 - !ruby/object:Gem::Dependency 
   type: :development
-  prerelease: false
-  name: rcov
   version_requirements: &id006 !ruby/object:Gem::Requirement 
     none: false
     requirements: 
@@ -106,10 +104,10 @@ dependencies:
         - 0
         version: "0"
   requirement: *id006
+  prerelease: false
+  name: rcov
 - !ruby/object:Gem::Dependency 
   type: :development
-  prerelease: false
-  name: geoip
   version_requirements: &id007 !ruby/object:Gem::Requirement 
     none: false
     requirements: 
@@ -120,6 +118,8 @@ dependencies:
         - 0
         version: "0"
   requirement: *id007
+  prerelease: false
+  name: geoip
 description: A tail(1)-like utility for nginx log files. It supports parsing, filtering and formatting individual log lines.
 email: pvandenberk@mac.com
 executables: 
@@ -168,6 +168,7 @@ files:
 - test/ntail/test_request.rb
 - test/ntail/test_status.rb
 - test/ntail/test_time_local.rb
+- test/ntail/test_uri.rb
 - test/test_ntail.rb
 has_rdoc: true
 homepage: http://github.com/pvdb/ntail
@@ -199,7 +200,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
 requirements: []
 
 rubyforge_project: 
-rubygems_version: 1.3.7
+rubygems_version: 1.4.1
 signing_key: 
 specification_version: 3
 summary: A tail(1)-like utility for nginx log files
@@ -216,4 +217,5 @@ test_files:
 - test/ntail/test_request.rb
 - test/ntail/test_status.rb
 - test/ntail/test_time_local.rb
+- test/ntail/test_uri.rb
 - test/test_ntail.rb